Twente University researchers have developed an online program that can determine the age and gender of Twitter users based on the content they post on the social network.
The program uses a list of words and sequences corresponding with different ages and specific genders based on data from nearly 3,000 Twitter users. When a username is entered, the program compares the last 200 tweets with the words and phrases in its database to determine the age and gender.
The distinction between men and women is often stereotypical, such as comments about football or nails. "In terms of age, younger users talk about themselves a lot more and use a lot of emoticons while older people use longer words and sentences," says Twente doctoral student Dong Nguyen.
The program has a margin of error of four years. The team is considering updating it for other languages and Facebook.
From Agence France-Presse
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA